© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129456
    Prev
    Next
    INDEX
    Explanations

    awards, committees, and judging panels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bidity
    -1.13
     +
    -1.05
     links
    -1.04
     Either
    -1.03
     ambos
    -1.03
     с
    -1.02
    lippe
    -1.02
     casi
    -1.00
    ()]);
    -0.98
    千年
    -0.98
    POSITIVE LOGITS
     judge
    1.34
     criteria
    1.33
     judging
    1.29
     verborgen
    1.16
     AllAfrica
    1.16
     geheim
    1.16
     criter
    1.15
     judges
    1.13
     criterios
    1.11
     selezion
    1.11
    Activations Density 0.021%

    No Known Activations